đ
Vgpo Rl 7b I1 Gguf dataset by mradermacher
â 41.1
đŦTechnical Deep Dive
Full Specifications [+]
đ Daily sync (03:00 UTC)
AI Summary: Based on Hugging Face metadata. Not a recommendation.
đĄī¸ Dataset Transparency Report
Technical metadata sourced from upstream repositories.
Open Metadata
đ Identity & Source
- id
- hf-dataset--mradermacher--vgpo-rl-7b-i1-gguf
- slug
- mradermacher--vgpo-rl-7b-i1-gguf
- source
- huggingface
- author
- mradermacher
- license
- MIT
- tags
- transformers, gguf, vgpo, reinforcement learning, multimodal reasoning, visual attention compensation, en, dataset:papogalaxy/papo_virl39k_train, base_model:muming0102/vgpo-rl-7b, base_model:quantized:muming0102/vgpo-rl-7b, license:mit, endpoints_compatible, region:us, imatrix, conversational
âī¸ Technical Specs
- architecture
- null
- params billions
- 7
- context length
- 4,096
- pipeline tag
đ Engagement & Metrics
- downloads
- 7,665
- stars
- 0
- forks
- 0
Data indexed from public sources. Updated daily.